Agentic & Tool Use benchmark
Remote Labor Index leaderboard
As of October 2026, GPT-6 Astra has the highest published Remote Labor Index score on Noometry at 20.8%, out of 14 models with results.
Last verified
About Remote Labor Index
Real paid freelance projects; the score is the share of projects completed at a level a client would accept.
- Category
- Agentic & Tool Use
- Introduced
- 2025
- Format
- Freelance projects
- Unit
- Percent (random guessing ≈ 0%)
- Official site
- www.remotelabor.ai
Top 14 models
- GPT-6 Astra 20.8%
- Claude Fable 5.1 17.9%
- Claude Fable 5 16.1%
- Claude Opus 4.8 8.3%
- GPT-5.5 6.3%
- Gemini 3.8 Flash 5.8%
- Gemini 3.7 Flash 5%
- Claude Opus 4.6 4.2%
- Claude Opus 4.5 3.8%
- GPT-5.2 2.5%
- Claude Sonnet 4.5 2.1%
- GPT-5 1.7%
- Gemini 3 Pro 1.3%
- Gemini 2.5 Pro 0.8%
Sponsored placements are available on pages like this one. Advertise on Noometry
All results
| # | Model | Provider | Score | Setting | Source | Date |
|---|---|---|---|---|---|---|
| 1 | GPT-6 Astra | OpenAI | 20.8% | Epoch AI | ||
| 2 | Claude Fable 5.1 | Anthropic | 17.9% | Epoch AI | ||
| 3 | Claude Fable 5 | Anthropic | 16.1% | Epoch AI | ||
| 4 | Claude Opus 4.8 | Anthropic | 8.3% | Epoch AI | ||
| 5 | GPT-5.5 | OpenAI | 6.3% | Epoch AI | ||
| 6 | Gemini 3.8 Flash | 5.8% | Epoch AI | |||
| 7 | Gemini 3.7 Flash | 5% | Epoch AI | |||
| 8 | Claude Opus 4.6 | Anthropic | 4.2% | Epoch AI | ||
| 9 | Claude Opus 4.5 | Anthropic | 3.8% | Epoch AI | ||
| 10 | GPT-5.2 | OpenAI | 2.5% | medium | Epoch AI | |
| 11 | Claude Sonnet 4.5 | Anthropic | 2.1% | Epoch AI | ||
| 12 | GPT-5 | OpenAI | 1.7% | Epoch AI | ||
| 13 | Gemini 3 Pro | 1.3% | Epoch AI | |||
| 14 | Gemini 2.5 Pro | 0.8% | Epoch AI |
Compare the leaders
Frequently asked questions
What does Remote Labor Index measure?
Real paid freelance projects; the score is the share of projects completed at a level a client would accept.
Which model has the highest Remote Labor Index score?
As of October 2026, GPT-6 Astra has the highest published Remote Labor Index score on Noometry at 20.8%, out of 14 models with results.